INDEX

Explanations

phrases related to conditions and requirements for understanding or performing tasks

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Shakspeare

-0.68

RSpec

-0.64

Efq

-0.61

Eſ

-0.60

 ―――――

-0.59

 hâte

-0.59

PositiveButton

-0.57

 ferrite

-0.57

 ikiwa

-0.56

Juf

-0.53

POSITIVE LOGITS

 eerst

0.88

 first

0.84

 must

0.82

まず

0.82

 firstly

0.81

 primero

0.80

 requires

0.77

서는

0.76

first

0.74

首先

0.74

Activations Density 0.330%

phrases related to conditions and requirements for understanding or performing tasks

No Comments

No Known Activations